hermes-agent/tests
Ben 1b1e30510a test(docker): repair dashboard tests broken by the insecure-opt-in fix
The Docker integration test job started failing on main after
fb5125362 ("docker: opt in to dashboard --insecure via env var").
Two distinct failures, both fallout from that change being more
behaviour-changing than the existing test harness anticipated.

Failure 1 — test_dashboard_port_override (silent regression in an
already-existing test)
The test starts the container with just HERMES_DASHBOARD=1, defaults
to host=0.0.0.0, no HERMES_DASHBOARD_OAUTH_CLIENT_ID, no
HERMES_DASHBOARD_INSECURE. Pre-fix that combination got --insecure
auto-injected by the s6 run script (anything non-loopback was
implicitly insecure), so the OAuth gate stayed off and start_server
bound the port. Post-fix the gate engages, no provider is
registered, and start_server raises SystemExit before binding —
under s6 the dashboard goes into a restart loop and the test's
/proc/net/tcp poll finds nothing.

Same silent regression was masking three sibling tests
(test_dashboard_slot_reports_up_when_enabled, test_dashboard_opt_in_starts,
test_dashboard_restarts_after_crash) — they all only sample pgrep
or s6-svstat and so caught the supervised process mid-restart
loop, appearing to pass while the dashboard was actually never
reaching a healthy state.

Fix: pin HERMES_DASHBOARD_INSECURE=1 on every test that enables
the dashboard but doesn't itself exercise the auth gate. Each
pinned site carries an inline comment pointing back to
test_dashboard_slot_reports_up_when_enabled for the full
rationale.

Failure 2 — test_dashboard_oauth_gate_engages_on_non_loopback_bind
(bug in the test I added in fb5125362)
The probe used urllib.request.urlopen() against /api/status. Under
the now-engaged OAuth gate /api/status no longer answers
unauthenticated callers (the gate middleware runs upstream of the
legacy _SESSION_TOKEN allowlist and 401s anything without a valid
session cookie). urlopen() raises HTTPError on the 401, the wrapper
treated that as "not ready yet", and the poll loop hit
timeout.

Fix: split the probe into a generic _http_probe() helper that
returns (status_code, body) for any HTTP response — including 401,
which IS the gate-engaged success signal. The helper feeds a
multi-line Python program over stdin via a POSIX heredoc so the
try/except branch reads naturally; far less fragile than the
earlier semicolon-laden -c one-liner.

The OAuth-gate test now verifies two independent observable
consequences of the gate being on:

  1. GET /api/auth/providers (publicly reachable through the gate
     so the login page can bootstrap) returns 200 with `nous` in
     the provider list — proves the bundled provider registered.
  2. GET /api/status returns 401 — proves the OAuth gate runs
     upstream of the legacy public-paths allowlist and is
     actively intercepting unauthenticated callers.

The insecure-opt-out test still hits /api/status, but now
asserts status_code == 200 first (proves the gate is bypassed)
before parsing the JSON for auth_required: false (proves the
gate-state flag is also correctly off).

Verified locally end-to-end against a fresh image build on a
real Docker daemon: all 41 tests under tests/docker/ pass in
2m38s, including the two formerly-failing dashboard tests and
the three sibling tests that were passing by accident.
2026-05-29 10:30:52 +10:00
..
acp test(acp): drop flaky runtime_calls[-1] tail-position assertion 2026-05-24 23:23:12 -07:00
acp_adapter feat(azure-foundry): add Microsoft Entra ID auth 2026-05-18 10:14:38 -07:00
agent feat: expose completed-turn message context to memory providers 2026-05-29 02:16:43 +05:30
cli fix(cli): /yolo in chat must enable session bypass, not just set env var 2026-05-28 12:10:21 -07:00
cron test(ci): harden two flaky tests against CI noise (#33675) 2026-05-27 23:15:41 -07:00
docker test(docker): repair dashboard tests broken by the insecure-opt-in fix 2026-05-29 10:30:52 +10:00
e2e refactor(gateway): migrate Discord adapter to bundled plugin (full Teams parity) 2026-05-22 14:21:41 -07:00
fakes
gateway fix(gateway): default media-delivery validation to denylist-only, restore .md delivery (#34022) 2026-05-28 11:32:36 -07:00
hermes_cli fix(kanban): SIGTERM on worker must terminate the process (#28181) 2026-05-28 11:59:58 -07:00
hermes_state feat(session_search): single-shape tool with discovery, scroll, browse — no LLM (#27590) 2026-05-17 23:28:45 -07:00
honcho_plugin fix(honcho): align peer-card read and write paths 2026-05-27 10:49:33 -07:00
integration chore(web): remove web_crawl tool + provider crawl plumbing (#33824) 2026-05-28 04:52:42 -07:00
openviking_plugin
plugins feat(hindsight): default recall_types to observation only 2026-05-28 13:07:20 -07:00
providers feat(openrouter): pass session_id in extra_body for sticky routing 2026-05-28 08:52:19 -07:00
run_agent feat: expose completed-turn message context to memory providers 2026-05-29 02:16:43 +05:30
scripts
skills fix(skills): add timeout to Google OAuth urlopen calls 2026-05-19 00:11:44 -07:00
stress docs: align kanban readiness docs and smoke tests 2026-05-18 21:07:03 -07:00
tools fix(mcp): resolve bare npx/npm/node against /usr/local/bin 2026-05-29 10:05:42 +10:00
tui_gateway chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
website
__init__.py
conftest.py test(dashboard-auth): strip HERMES_DASHBOARD_OAUTH_* env vars in hermetic fixture 2026-05-27 02:12:27 -07:00
run_interrupt_test.py
test_account_usage.py
test_atomic_replace_symlinks.py
test_base_url_hostname.py
test_batch_runner_checkpoint.py
test_bitwarden_secrets.py perf(cli): cut hermes startup 63% — flip head-to-head vs codex (#31968) 2026-05-25 03:06:39 -07:00
test_cli_file_drop.py
test_cli_manual_compress.py fix(tests): catch up six stale tests after compression/aux/kanban changes (#28465) 2026-05-18 21:43:59 -07:00
test_cli_skin_integration.py
test_ctx_halving_fix.py fix: stop probe stepdown without provider context limit 2026-05-28 12:26:53 -07:00
test_docker_home_override_scripts.py docker: opt in to dashboard --insecure via env var, never derive from bind host 2026-05-29 09:56:40 +10:00
test_empty_model_fallback.py
test_env_loader_secret_sources.py fix(secrets): only apply external secrets once per HERMES_HOME per process (#32271) 2026-05-25 15:18:55 -07:00
test_evidence_store.py
test_gateway_streaming_nested_config.py
test_get_tool_definitions_cache_isolation.py
test_hermes_bootstrap.py
test_hermes_constants.py fix(security): guard os.chmod(parent) against / and top-level dirs 2026-05-20 22:56:55 -07:00
test_hermes_home_profile_warning.py
test_hermes_logging.py fix(tests): catch up 25 stale tests after recent merges (#28626) 2026-05-19 01:28:32 -07:00
test_hermes_state.py fix(kanban): skip redundant WAL pragma on already-WAL connections 2026-05-27 14:31:55 -07:00
test_hermes_state_wal_fallback.py fix(kanban): skip redundant WAL pragma on already-WAL connections 2026-05-27 14:31:55 -07:00
test_honcho_client_config.py
test_honcho_session_context.py fix(honcho): align user context peer perspective 2026-05-27 10:49:33 -07:00
test_install_sh_browser_install.py
test_install_sh_pythonpath_sanitization.py
test_install_sh_root_fhs_uv_python_path.py test(install): harden uv-python-path regression test against future drift 2026-05-27 13:55:51 -07:00
test_install_sh_setup_wizard_tty_probe.py
test_install_sh_symlink_stomp.py
test_install_sh_termux_network_prereqs.py
test_ipv4_preference.py
test_lazy_session_regressions.py
test_lint_config.py
test_live_system_guard_self_test.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_mcp_serve.py
test_mini_swe_runner.py
test_minimax_model_validation.py
test_minimax_oauth.py fix(minimax-oauth): refresh short-lived access tokens per request (#30619) 2026-05-22 15:16:15 -07:00
test_minisweagent_path.py
test_model_picker_scroll.py
test_model_tools.py
test_model_tools_async_bridge.py
test_ollama_num_ctx.py
test_package_json_lazy_deps.py fix(update): make Camofox lazy-installed instead of eager (#27055) 2026-05-16 12:15:45 -07:00
test_packaging_metadata.py
test_plugin_skills.py
test_process_loop_event_loop_warning.py
test_project_metadata.py remove Vercel AI Gateway and Vercel Sandbox (#33067) 2026-05-27 00:43:32 -07:00
test_retry_utils.py
test_run_tests_parallel.py test: use subprocesses for each test file (#29016) 2026-05-21 16:40:04 +05:30
test_sanitize_tool_error.py security: sanitize tool error strings before injecting into model context (#26823) 2026-05-16 00:57:39 -07:00
test_sql_injection.py
test_subprocess_home_isolation.py fix: avoid process-wide cron profile home mutation 2026-05-18 17:39:50 +00:00
test_termux_all_extra_compat.py
test_timezone.py chore: ruff auto-fix PLR6201 resweep — tuple → set in membership tests (#27355) 2026-05-17 02:29:41 -07:00
test_toolset_distributions.py
test_toolsets.py
test_trajectory_compressor.py
test_trajectory_compressor_async.py
test_transform_llm_output_hook.py
test_transform_tool_result_hook.py
test_tui_gateway_server.py feat: add TUI session orchestrator 2026-05-26 20:51:59 -07:00
test_utils_truthy_values.py
test_yuanbao_integration.py
test_yuanbao_markdown.py
test_yuanbao_pipeline.py
test_yuanbao_proto.py